aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Target/X86/X86RegisterInfo.cpp
blob: 130cb61cdde24e4926e6e6e10b98a76d70dc9580 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
//===-- X86RegisterInfo.cpp - X86 Register Information --------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file contains the X86 implementation of the TargetRegisterInfo class.
// This file is responsible for the frame pointer elimination optimization
// on X86.
//
//===----------------------------------------------------------------------===//

#include "X86RegisterInfo.h"
#include "X86FrameLowering.h"
#include "X86MachineFunctionInfo.h"
#include "X86Subtarget.h"
#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/CodeGen/LiveRegMatrix.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/TargetFrameLowering.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Type.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"

using namespace llvm;

#define GET_REGINFO_TARGET_DESC
#include "X86GenRegisterInfo.inc"

static cl::opt<bool>
EnableBasePointer("x86-use-base-pointer", cl::Hidden, cl::init(true),
          cl::desc("Enable use of a base pointer for complex stack frames"));

X86RegisterInfo::X86RegisterInfo(const Triple &TT)
    : X86GenRegisterInfo((TT.isArch64Bit() ? X86::RIP : X86::EIP),
                         X86_MC::getDwarfRegFlavour(TT, false),
                         X86_MC::getDwarfRegFlavour(TT, true),
                         (TT.isArch64Bit() ? X86::RIP : X86::EIP)) {
  X86_MC::initLLVMToSEHAndCVRegMapping(this);

  // Cache some information.
  Is64Bit = TT.isArch64Bit();
  IsWin64 = Is64Bit && TT.isOSWindows();

  // Use a callee-saved register as the base pointer.  These registers must
  // not conflict with any ABI requirements.  For example, in 32-bit mode PIC
  // requires GOT in the EBX register before function calls via PLT GOT pointer.
  if (Is64Bit) {
    SlotSize = 8;
    // This matches the simplified 32-bit pointer code in the data layout
    // computation.
    // FIXME: Should use the data layout?
    bool Use64BitReg = !TT.isX32();
    StackPtr = Use64BitReg ? X86::RSP : X86::ESP;
    FramePtr = Use64BitReg ? X86::RBP : X86::EBP;
    BasePtr = Use64BitReg ? X86::RBX : X86::EBX;
  } else {
    SlotSize = 4;
    StackPtr = X86::ESP;
    FramePtr = X86::EBP;
    BasePtr = X86::ESI;
  }
}

int
X86RegisterInfo::getSEHRegNum(unsigned i) const {
  return getEncodingValue(i);
}

const TargetRegisterClass *
X86RegisterInfo::getSubClassWithSubReg(const TargetRegisterClass *RC,
                                       unsigned Idx) const {
  // The sub_8bit sub-register index is more constrained in 32-bit mode.
  // It behaves just like the sub_8bit_hi index.
  if (!Is64Bit && Idx == X86::sub_8bit)
    Idx = X86::sub_8bit_hi;

  // Forward to TableGen's default version.
  return X86GenRegisterInfo::getSubClassWithSubReg(RC, Idx);
}

const TargetRegisterClass *
X86RegisterInfo::getMatchingSuperRegClass(const TargetRegisterClass *A,
                                          const TargetRegisterClass *B,
                                          unsigned SubIdx) const {
  // The sub_8bit sub-register index is more constrained in 32-bit mode.
  if (!Is64Bit && SubIdx == X86::sub_8bit) {
    A = X86GenRegisterInfo::getSubClassWithSubReg(A, X86::sub_8bit_hi);
    if (!A)
      return nullptr;
  }
  return X86GenRegisterInfo::getMatchingSuperRegClass(A, B, SubIdx);
}

const TargetRegisterClass *
X86RegisterInfo::getLargestLegalSuperClass(const TargetRegisterClass *RC,
                                           const MachineFunction &MF) const {
  // Don't allow super-classes of GR8_NOREX.  This class is only used after
  // extracting sub_8bit_hi sub-registers.  The H sub-registers cannot be copied
  // to the full GR8 register class in 64-bit mode, so we cannot allow the
  // reigster class inflation.
  //
  // The GR8_NOREX class is always used in a way that won't be constrained to a
  // sub-class, so sub-classes like GR8_ABCD_L are allowed to expand to the
  // full GR8 class.
  if (RC == &X86::GR8_NOREXRegClass)
    return RC;

  const X86Subtarget &Subtarget = MF.getSubtarget<X86Subtarget>();

  const TargetRegisterClass *Super = RC;
  TargetRegisterClass::sc_iterator I = RC->getSuperClasses();
  do {
    switch (Super->getID()) {
    case X86::FR32RegClassID:
    case X86::FR64RegClassID:
      // If AVX-512 isn't supported we should only inflate to these classes.
      if (!Subtarget.hasAVX512() &&
          getRegSizeInBits(*Super) == getRegSizeInBits(*RC))
        return Super;
      break;
    case X86::VR128RegClassID:
    case X86::VR256RegClassID:
      // If VLX isn't supported we should only inflate to these classes.
      if (!Subtarget.hasVLX() &&
          getRegSizeInBits(*Super) == getRegSizeInBits(*RC))
        return Super;
      break;
    case X86::VR128XRegClassID:
    case X86::VR256XRegClassID:
      // If VLX isn't support we shouldn't inflate to these classes.
      if (Subtarget.hasVLX() &&
          getRegSizeInBits(*Super) == getRegSizeInBits(*RC))
        return Super;
      break;
    case X86::FR32XRegClassID:
    case X86::FR64XRegClassID:
      // If AVX-512 isn't support we shouldn't inflate to these classes.
      if (Subtarget.hasAVX512() &&
          getRegSizeInBits(*Super) == getRegSizeInBits(*RC))
        return Super;
      break;
    case X86::GR8RegClassID:
    case X86::GR16RegClassID:
    case X86::GR32RegClassID:
    case X86::GR64RegClassID:
    case X86::RFP32RegClassID:
    case X86::RFP64RegClassID:
    case X86::RFP80RegClassID:
    case X86::VR512_0_15RegClassID:
    case X86::VR512RegClassID:
      // Don't return a super-class that would shrink the spill size.
      // That can happen with the vector and float classes.
      if (getRegSizeInBits(*Super) == getRegSizeInBits(*RC))
        return Super;
    }
    Super = *I++;
  } while (Super);
  return RC;
}

const TargetRegisterClass *
X86RegisterInfo::getPointerRegClass(const MachineFunction &MF,
                                    unsigned Kind) const {
  const X86Subtarget &Subtarget = MF.getSubtarget<X86Subtarget>();
  switch (Kind) {
  default: llvm_unreachable("Unexpected Kind in getPointerRegClass!");
  case 0: // Normal GPRs.
    if (Subtarget.isTarget64BitLP64())
      return &X86::GR64RegClass;
    // If the target is 64bit but we have been told to use 32bit addresses,
    // we can still use 64-bit register as long as we know the high bits
    // are zeros.
    // Reflect that in the returned register class.
    if (Is64Bit) {
      // When the target also allows 64-bit frame pointer and we do have a
      // frame, this is fine to use it for the address accesses as well.
      const X86FrameLowering *TFI = getFrameLowering(MF);
      return TFI->hasFP(MF) && TFI->Uses64BitFramePtr
                 ? &X86::LOW32_ADDR_ACCESS_RBPRegClass
                 : &X86::LOW32_ADDR_ACCESSRegClass;
    }
    return &X86::GR32RegClass;
  case 1: // Normal GPRs except the stack pointer (for encoding reasons).
    if (Subtarget.isTarget64BitLP64())
      return &X86::GR64_NOSPRegClass;
    // NOSP does not contain RIP, so no special case here.
    return &X86::GR32_NOSPRegClass;
  case 2: // NOREX GPRs.
    if (Subtarget.isTarget64BitLP64())
      return &X86::GR64_NOREXRegClass;
    return &X86::GR32_NOREXRegClass;
  case 3: // NOREX GPRs except the stack pointer (for encoding reasons).
    if (Subtarget.isTarget64BitLP64())
      return &X86::GR64_NOREX_NOSPRegClass;
    // NOSP does not contain RIP, so no special case here.
    return &X86::GR32_NOREX_NOSPRegClass;
  case 4: // Available for tailcall (not callee-saved GPRs).
    return getGPRsForTailCall(MF);
  }
}

bool X86RegisterInfo::shouldRewriteCopySrc(const TargetRegisterClass *DefRC,
                                           unsigned DefSubReg,
                                           const TargetRegisterClass *SrcRC,
                                           unsigned SrcSubReg) const {
  // Prevent rewriting a copy where the destination size is larger than the
  // input size. See PR41619.
  // FIXME: Should this be factored into the base implementation somehow.
  if (DefRC->hasSuperClassEq(&X86::GR64RegClass) && DefSubReg == 0 &&
      SrcRC->hasSuperClassEq(&X86::GR64RegClass) && SrcSubReg == X86::sub_32bit)
    return false;

  return TargetRegisterInfo::shouldRewriteCopySrc(DefRC, DefSubReg,
                                                  SrcRC, SrcSubReg);
}

const TargetRegisterClass *
X86RegisterInfo::getGPRsForTailCall(const MachineFunction &MF) const {
  const Function &F = MF.getFunction();
  if (IsWin64 || (F.getCallingConv() == CallingConv::Win64))
    return &X86::GR64_TCW64RegClass;
  else if (Is64Bit)
    return &X86::GR64_TCRegClass;

  bool hasHipeCC = (F.getCallingConv() == CallingConv::HiPE);
  if (hasHipeCC)
    return &X86::GR32RegClass;
  return &X86::GR32_TCRegClass;
}

const TargetRegisterClass *
X86RegisterInfo::getCrossCopyRegClass(const TargetRegisterClass *RC) const {
  if (RC == &X86::CCRRegClass) {
    if (Is64Bit)
      return &X86::GR64RegClass;
    else
      return &X86::GR32RegClass;
  }
  return RC;
}

unsigned
X86RegisterInfo::getRegPressureLimit(const TargetRegisterClass *RC,
                                     MachineFunction &MF) const {
  const X86FrameLowering *TFI = getFrameLowering(MF);

  unsigned FPDiff = TFI->hasFP(MF) ? 1 : 0;
  switch (RC->getID()) {
  default:
    return 0;
  case X86::GR32RegClassID:
    return 4 - FPDiff;
  case X86::GR64RegClassID:
    return 12 - FPDiff;
  case X86::VR128RegClassID:
    return Is64Bit ? 10 : 4;
  case X86::VR64RegClassID:
    return 4;
  }
}

const MCPhysReg *
X86RegisterInfo::getCalleeSavedRegs(const MachineFunction *MF) const {
  assert(MF && "MachineFunction required");

  const X86Subtarget &Subtarget = MF->getSubtarget<X86Subtarget>();
  const Function &F = MF->getFunction();
  bool HasSSE = Subtarget.hasSSE1();
  bool HasAVX = Subtarget.hasAVX();
  bool HasAVX512 = Subtarget.hasAVX512();
  bool CallsEHReturn = MF->callsEHReturn();

  CallingConv::ID CC = F.getCallingConv();

  // If attribute NoCallerSavedRegisters exists then we set X86_INTR calling
  // convention because it has the CSR list.
  if (MF->getFunction().hasFnAttribute("no_caller_saved_registers"))
    CC = CallingConv::X86_INTR;

  // If atribute specified, override the CSRs normally specified by the
  // calling convention and use the empty set instead.
  if (MF->getFunction().hasFnAttribute("no_callee_saved_registers"))
    return CSR_NoRegs_SaveList;

  switch (CC) {
  case CallingConv::GHC:
  case CallingConv::HiPE:
    return CSR_NoRegs_SaveList;
  case CallingConv::AnyReg:
    if (HasAVX)
      return CSR_64_AllRegs_AVX_SaveList;
    return CSR_64_AllRegs_SaveList;
  case CallingConv::PreserveMost:
    return CSR_64_RT_MostRegs_SaveList;
  case CallingConv::PreserveAll:
    if (HasAVX)
      return CSR_64_RT_AllRegs_AVX_SaveList;
    return CSR_64_RT_AllRegs_SaveList;
  case CallingConv::CXX_FAST_TLS:
    if (Is64Bit)
      return MF->getInfo<X86MachineFunctionInfo>()->isSplitCSR() ?
             CSR_64_CXX_TLS_Darwin_PE_SaveList : CSR_64_TLS_Darwin_SaveList;
    break;
  case CallingConv::Intel_OCL_BI: {
    if (HasAVX512 && IsWin64)
      return CSR_Win64_Intel_OCL_BI_AVX512_SaveList;
    if (HasAVX512 && Is64Bit)
      return CSR_64_Intel_OCL_BI_AVX512_SaveList;
    if (HasAVX && IsWin64)
      return CSR_Win64_Intel_OCL_BI_AVX_SaveList;
    if (HasAVX && Is64Bit)
      return CSR_64_Intel_OCL_BI_AVX_SaveList;
    if (!HasAVX && !IsWin64 && Is64Bit)
      return CSR_64_Intel_OCL_BI_SaveList;
    break;
  }
  case CallingConv::HHVM:
    return CSR_64_HHVM_SaveList;
  case CallingConv::X86_RegCall:
    if (Is64Bit) {
      if (IsWin64) {
        return (HasSSE ? CSR_Win64_RegCall_SaveList :
                         CSR_Win64_RegCall_NoSSE_SaveList);
      } else {
        return (HasSSE ? CSR_SysV64_RegCall_SaveList :
                         CSR_SysV64_RegCall_NoSSE_SaveList);
      }
    } else {
      return (HasSSE ? CSR_32_RegCall_SaveList :
                       CSR_32_RegCall_NoSSE_SaveList);
    }
  case CallingConv::CFGuard_Check:
    assert(!Is64Bit && "CFGuard check mechanism only used on 32-bit X86");
    return (HasSSE ? CSR_Win32_CFGuard_Check_SaveList
                   : CSR_Win32_CFGuard_Check_NoSSE_SaveList);
  case CallingConv::Cold:
    if (Is64Bit)
      return CSR_64_MostRegs_SaveList;
    break;
  case CallingConv::Win64:
    if (!HasSSE)
      return CSR_Win64_NoSSE_SaveList;
    return CSR_Win64_SaveList;
  case CallingConv::SwiftTail:
    if (!Is64Bit)
      return CSR_32_SaveList;
    return IsWin64 ? CSR_Win64_SwiftTail_SaveList : CSR_64_SwiftTail_SaveList;
  case CallingConv::X86_64_SysV:
    if (CallsEHReturn)
      return CSR_64EHRet_SaveList;
    return CSR_64_SaveList;
  case CallingConv::X86_INTR:
    if (Is64Bit) {
      if (HasAVX512)
        return CSR_64_AllRegs_AVX512_SaveList;
      if (HasAVX)
        return CSR_64_AllRegs_AVX_SaveList;
      if (HasSSE)
        return CSR_64_AllRegs_SaveList;
      return CSR_64_AllRegs_NoSSE_SaveList;
    } else {
      if (HasAVX512)
        return CSR_32_AllRegs_AVX512_SaveList;
      if (HasAVX)
        return CSR_32_AllRegs_AVX_SaveList;
      if (HasSSE)
        return CSR_32_AllRegs_SSE_SaveList;
      return CSR_32_AllRegs_SaveList;
    }
  default:
    break;
  }

  if (Is64Bit) {
    bool IsSwiftCC = Subtarget.getTargetLowering()->supportSwiftError() &&
                     F.getAttributes().hasAttrSomewhere(Attribute::SwiftError);
    if (IsSwiftCC)
      return IsWin64 ? CSR_Win64_SwiftError_SaveList
                     : CSR_64_SwiftError_SaveList;

    if (IsWin64)
      return HasSSE ? CSR_Win64_SaveList : CSR_Win64_NoSSE_SaveList;
    if (CallsEHReturn)
      return CSR_64EHRet_SaveList;
    return CSR_64_SaveList;
  }

  return CallsEHReturn ? CSR_32EHRet_SaveList : CSR_32_SaveList;
}

const MCPhysReg *X86RegisterInfo::getCalleeSavedRegsViaCopy(
    const MachineFunction *MF) const {
  assert(MF && "Invalid MachineFunction pointer.");
  if (MF->getFunction().getCallingConv() == CallingConv::CXX_FAST_TLS &&
      MF->getInfo<X86MachineFunctionInfo>()->isSplitCSR())
    return CSR_64_CXX_TLS_Darwin_ViaCopy_SaveList;
  return nullptr;
}

const uint32_t *
X86RegisterInfo::getCallPreservedMask(const MachineFunction &MF,
                                      CallingConv::ID CC) const {
  const X86Subtarget &Subtarget = MF.getSubtarget<X86Subtarget>();
  bool HasSSE = Subtarget.hasSSE1();
  bool HasAVX = Subtarget.hasAVX();
  bool HasAVX512 = Subtarget.hasAVX512();

  switch (CC) {
  case CallingConv::GHC:
  case CallingConv::HiPE:
    return CSR_NoRegs_RegMask;
  case CallingConv::AnyReg:
    if (HasAVX)
      return CSR_64_AllRegs_AVX_RegMask;
    return CSR_64_AllRegs_RegMask;
  case CallingConv::PreserveMost:
    return CSR_64_RT_MostRegs_RegMask;
  case CallingConv::PreserveAll:
    if (HasAVX)
      return CSR_64_RT_AllRegs_AVX_RegMask;
    return CSR_64_RT_AllRegs_RegMask;
  case CallingConv::CXX_FAST_TLS:
    if (Is64Bit)
      return CSR_64_TLS_Darwin_RegMask;
    break;
  case CallingConv::Intel_OCL_BI: {
    if (HasAVX512 && IsWin64)
      return CSR_Win64_Intel_OCL_BI_AVX512_RegMask;
    if (HasAVX512 && Is64Bit)
      return CSR_64_Intel_OCL_BI_AVX512_RegMask;
    if (HasAVX && IsWin64)
      return CSR_Win64_Intel_OCL_BI_AVX_RegMask;
    if (HasAVX && Is64Bit)
      return CSR_64_Intel_OCL_BI_AVX_RegMask;
    if (!HasAVX && !IsWin64 && Is64Bit)
      return CSR_64_Intel_OCL_BI_RegMask;
    break;
  }
  case CallingConv::HHVM:
    return CSR_64_HHVM_RegMask;
  case CallingConv::X86_RegCall:
    if (Is64Bit) {
      if (IsWin64) {
        return (HasSSE ? CSR_Win64_RegCall_RegMask :
                         CSR_Win64_RegCall_NoSSE_RegMask);
      } else {
        return (HasSSE ? CSR_SysV64_RegCall_RegMask :
                         CSR_SysV64_RegCall_NoSSE_RegMask);
      }
    } else {
      return (HasSSE ? CSR_32_RegCall_RegMask :
                       CSR_32_RegCall_NoSSE_RegMask);
    }
  case CallingConv::CFGuard_Check:
    assert(!Is64Bit && "CFGuard check mechanism only used on 32-bit X86");
    return (HasSSE ? CSR_Win32_CFGuard_Check_RegMask
                   : CSR_Win32_CFGuard_Check_NoSSE_RegMask);
  case CallingConv::Cold:
    if (Is64Bit)
      return CSR_64_MostRegs_RegMask;
    break;
  case CallingConv::Win64:
    return CSR_Win64_RegMask;
  case CallingConv::SwiftTail:
    if (!Is64Bit)
      return CSR_32_RegMask;
    return IsWin64 ? CSR_Win64_SwiftTail_RegMask : CSR_64_SwiftTail_RegMask;
  case CallingConv::X86_64_SysV:
    return CSR_64_RegMask;
  case CallingConv::X86_INTR:
    if (Is64Bit) {
      if (HasAVX512)
        return CSR_64_AllRegs_AVX512_RegMask;
      if (HasAVX)
        return CSR_64_AllRegs_AVX_RegMask;
      if (HasSSE)
        return CSR_64_AllRegs_RegMask;
      return CSR_64_AllRegs_NoSSE_RegMask;
    } else {
      if (HasAVX512)
        return CSR_32_AllRegs_AVX512_RegMask;
      if (HasAVX)
        return CSR_32_AllRegs_AVX_RegMask;
      if (HasSSE)
        return CSR_32_AllRegs_SSE_RegMask;
      return CSR_32_AllRegs_RegMask;
    }
  default:
    break;
  }

  // Unlike getCalleeSavedRegs(), we don't have MMI so we can't check
  // callsEHReturn().
  if (Is64Bit) {
    const Function &F = MF.getFunction();
    bool IsSwiftCC = Subtarget.getTargetLowering()->supportSwiftError() &&
                     F.getAttributes().hasAttrSomewhere(Attribute::SwiftError);
    if (IsSwiftCC)
      return IsWin64 ? CSR_Win64_SwiftError_RegMask : CSR_64_SwiftError_RegMask;

    return IsWin64 ? CSR_Win64_RegMask : CSR_64_RegMask;
  }

  return CSR_32_RegMask;
}

const uint32_t*
X86RegisterInfo::getNoPreservedMask() const {
  return CSR_NoRegs_RegMask;
}

const uint32_t *X86RegisterInfo::getDarwinTLSCallPreservedMask() const {
  return CSR_64_TLS_Darwin_RegMask;
}

BitVector X86RegisterInfo::getReservedRegs(const MachineFunction &MF) const {
  BitVector Reserved(getNumRegs());
  const X86FrameLowering *TFI = getFrameLowering(MF);

  // Set the floating point control register as reserved.
  Reserved.set(X86::FPCW);

  // Set the floating point status register as reserved.
  Reserved.set(X86::FPSW);

  // Set the SIMD floating point control register as reserved.
  Reserved.set(X86::MXCSR);

  // Set the stack-pointer register and its aliases as reserved.
  for (const MCPhysReg &SubReg : subregs_inclusive(X86::RSP))
    Reserved.set(SubReg);

  // Set the Shadow Stack Pointer as reserved.
  Reserved.set(X86::SSP);

  // Set the instruction pointer register and its aliases as reserved.
  for (const MCPhysReg &SubReg : subregs_inclusive(X86::RIP))
    Reserved.set(SubReg);

  // Set the frame-pointer register and its aliases as reserved if needed.
  if (TFI->hasFP(MF)) {
    for (const MCPhysReg &SubReg : subregs_inclusive(X86::RBP))
      Reserved.set(SubReg);
  }

  // Set the base-pointer register and its aliases as reserved if needed.
  if (hasBasePointer(MF)) {
    CallingConv::ID CC = MF.getFunction().getCallingConv();
    const uint32_t *RegMask = getCallPreservedMask(MF, CC);
    if (MachineOperand::clobbersPhysReg(RegMask, getBaseRegister()))
      report_fatal_error(
        "Stack realignment in presence of dynamic allocas is not supported with"
        "this calling convention.");

    Register BasePtr = getX86SubSuperRegister(getBaseRegister(), 64);
    for (const MCPhysReg &SubReg : subregs_inclusive(BasePtr))
      Reserved.set(SubReg);
  }

  // Mark the segment registers as reserved.
  Reserved.set(X86::CS);
  Reserved.set(X86::SS);
  Reserved.set(X86::DS);
  Reserved.set(X86::ES);
  Reserved.set(X86::FS);
  Reserved.set(X86::GS);

  // Mark the floating point stack registers as reserved.
  for (unsigned n = 0; n != 8; ++n)
    Reserved.set(X86::ST0 + n);

  // Reserve the registers that only exist in 64-bit mode.
  if (!Is64Bit) {
    // These 8-bit registers are part of the x86-64 extension even though their
    // super-registers are old 32-bits.
    Reserved.set(X86::SIL);
    Reserved.set(X86::DIL);
    Reserved.set(X86::BPL);
    Reserved.set(X86::SPL);
    Reserved.set(X86::SIH);
    Reserved.set(X86::DIH);
    Reserved.set(X86::BPH);
    Reserved.set(X86::SPH);

    for (unsigned n = 0; n != 8; ++n) {
      // R8, R9, ...
      for (MCRegAliasIterator AI(X86::R8 + n, this, true); AI.isValid(); ++AI)
        Reserved.set(*AI);

      // XMM8, XMM9, ...
      for (MCRegAliasIterator AI(X86::XMM8 + n, this, true); AI.isValid(); ++AI)
        Reserved.set(*AI);
    }
  }
  if (!Is64Bit || !MF.getSubtarget<X86Subtarget>().hasAVX512()) {
    for (unsigned n = 16; n != 32; ++n) {
      for (MCRegAliasIterator AI(X86::XMM0 + n, this, true); AI.isValid(); ++AI)
        Reserved.set(*AI);
    }
  }

  assert(checkAllSuperRegsMarked(Reserved,
                                 {X86::SIL, X86::DIL, X86::BPL, X86::SPL,
                                  X86::SIH, X86::DIH, X86::BPH, X86::SPH}));
  return Reserved;
}

void X86RegisterInfo::adjustStackMapLiveOutMask(uint32_t *Mask) const {
  // Check if the EFLAGS register is marked as live-out. This shouldn't happen,
  // because the calling convention defines the EFLAGS register as NOT
  // preserved.
  //
  // Unfortunatelly the EFLAGS show up as live-out after branch folding. Adding
  // an assert to track this and clear the register afterwards to avoid
  // unnecessary crashes during release builds.
  assert(!(Mask[X86::EFLAGS / 32] & (1U << (X86::EFLAGS % 32))) &&
         "EFLAGS are not live-out from a patchpoint.");

  // Also clean other registers that don't need preserving (IP).
  for (auto Reg : {X86::EFLAGS, X86::RIP, X86::EIP, X86::IP})
    Mask[Reg / 32] &= ~(1U << (Reg % 32));
}

//===----------------------------------------------------------------------===//
// Stack Frame Processing methods
//===----------------------------------------------------------------------===//

static bool CantUseSP(const MachineFrameInfo &MFI) {
  return MFI.hasVarSizedObjects() || MFI.hasOpaqueSPAdjustment();
}

bool X86RegisterInfo::hasBasePointer(const MachineFunction &MF) const {
  const X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
  if (X86FI->hasPreallocatedCall())
    return true;

  const MachineFrameInfo &MFI = MF.getFrameInfo();

  if (!EnableBasePointer)
    return false;

  // When we need stack realignment, we can't address the stack from the frame
  // pointer.  When we have dynamic allocas or stack-adjusting inline asm, we
  // can't address variables from the stack pointer.  MS inline asm can
  // reference locals while also adjusting the stack pointer.  When we can't
  // use both the SP and the FP, we need a separate base pointer register.
  bool CantUseFP = hasStackRealignment(MF);
  return CantUseFP && CantUseSP(MFI);
}

bool X86RegisterInfo::canRealignStack(const MachineFunction &MF) const {
  if (!TargetRegisterInfo::canRealignStack(MF))
    return false;

  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const MachineRegisterInfo *MRI = &MF.getRegInfo();

  // Stack realignment requires a frame pointer.  If we already started
  // register allocation with frame pointer elimination, it is too late now.
  if (!MRI->canReserveReg(FramePtr))
    return false;

  // If a base pointer is necessary.  Check that it isn't too late to reserve
  // it.
  if (CantUseSP(MFI))
    return MRI->canReserveReg(BasePtr);
  return true;
}

// tryOptimizeLEAtoMOV - helper function that tries to replace a LEA instruction
// of the form 'lea (%esp), %ebx' --> 'mov %esp, %ebx'.
// TODO: In this case we should be really trying first to entirely eliminate
// this instruction which is a plain copy.
static bool tryOptimizeLEAtoMOV(MachineBasicBlock::iterator II) {
  MachineInstr &MI = *II;
  unsigned Opc = II->getOpcode();
  // Check if this is a LEA of the form 'lea (%esp), %ebx'
  if ((Opc != X86::LEA32r && Opc != X86::LEA64r && Opc != X86::LEA64_32r) ||
      MI.getOperand(2).getImm() != 1 ||
      MI.getOperand(3).getReg() != X86::NoRegister ||
      MI.getOperand(4).getImm() != 0 ||
      MI.getOperand(5).getReg() != X86::NoRegister)
    return false;
  Register BasePtr = MI.getOperand(1).getReg();
  // In X32 mode, ensure the base-pointer is a 32-bit operand, so the LEA will
  // be replaced with a 32-bit operand MOV which will zero extend the upper
  // 32-bits of the super register.
  if (Opc == X86::LEA64_32r)
    BasePtr = getX86SubSuperRegister(BasePtr, 32);
  Register NewDestReg = MI.getOperand(0).getReg();
  const X86InstrInfo *TII =
      MI.getParent()->getParent()->getSubtarget<X86Subtarget>().getInstrInfo();
  TII->copyPhysReg(*MI.getParent(), II, MI.getDebugLoc(), NewDestReg, BasePtr,
                   MI.getOperand(1).isKill());
  MI.eraseFromParent();
  return true;
}

static bool isFuncletReturnInstr(MachineInstr &MI) {
  switch (MI.getOpcode()) {
  case X86::CATCHRET:
  case X86::CLEANUPRET:
    return true;
  default:
    return false;
  }
  llvm_unreachable("impossible");
}

void
X86RegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator II,
                                     int SPAdj, unsigned FIOperandNum,
                                     RegScavenger *RS) const {
  MachineInstr &MI = *II;
  MachineBasicBlock &MBB = *MI.getParent();
  MachineFunction &MF = *MBB.getParent();
  MachineBasicBlock::iterator MBBI = MBB.getFirstTerminator();
  bool IsEHFuncletEpilogue = MBBI == MBB.end() ? false
                                               : isFuncletReturnInstr(*MBBI);
  const X86FrameLowering *TFI = getFrameLowering(MF);
  int FrameIndex = MI.getOperand(FIOperandNum).getIndex();

  // Determine base register and offset.
  int FIOffset;
  Register BasePtr;
  if (MI.isReturn()) {
    assert((!hasStackRealignment(MF) ||
            MF.getFrameInfo().isFixedObjectIndex(FrameIndex)) &&
           "Return instruction can only reference SP relative frame objects");
    FIOffset =
        TFI->getFrameIndexReferenceSP(MF, FrameIndex, BasePtr, 0).getFixed();
  } else if (TFI->Is64Bit && (MBB.isEHFuncletEntry() || IsEHFuncletEpilogue)) {
    FIOffset = TFI->getWin64EHFrameIndexRef(MF, FrameIndex, BasePtr);
  } else {
    FIOffset = TFI->getFrameIndexReference(MF, FrameIndex, BasePtr).getFixed();
  }

  // LOCAL_ESCAPE uses a single offset, with no register. It only works in the
  // simple FP case, and doesn't work with stack realignment. On 32-bit, the
  // offset is from the traditional base pointer location.  On 64-bit, the
  // offset is from the SP at the end of the prologue, not the FP location. This
  // matches the behavior of llvm.frameaddress.
  unsigned Opc = MI.getOpcode();
  if (Opc == TargetOpcode::LOCAL_ESCAPE) {
    MachineOperand &FI = MI.getOperand(FIOperandNum);
    FI.ChangeToImmediate(FIOffset);
    return;
  }

  // For LEA64_32r when BasePtr is 32-bits (X32) we can use full-size 64-bit
  // register as source operand, semantic is the same and destination is
  // 32-bits. It saves one byte per lea in code since 0x67 prefix is avoided.
  // Don't change BasePtr since it is used later for stack adjustment.
  Register MachineBasePtr = BasePtr;
  if (Opc == X86::LEA64_32r && X86::GR32RegClass.contains(BasePtr))
    MachineBasePtr = getX86SubSuperRegister(BasePtr, 64);

  // This must be part of a four operand memory reference.  Replace the
  // FrameIndex with base register.  Add an offset to the offset.
  MI.getOperand(FIOperandNum).ChangeToRegister(MachineBasePtr, false);

  if (BasePtr == StackPtr)
    FIOffset += SPAdj;

  // The frame index format for stackmaps and patchpoints is different from the
  // X86 format. It only has a FI and an offset.
  if (Opc == TargetOpcode::STACKMAP || Opc == TargetOpcode::PATCHPOINT) {
    assert(BasePtr == FramePtr && "Expected the FP as base register");
    int64_t Offset = MI.getOperand(FIOperandNum + 1).getImm() + FIOffset;
    MI.getOperand(FIOperandNum + 1).ChangeToImmediate(Offset);
    return;
  }

  if (MI.getOperand(FIOperandNum+3).isImm()) {
    // Offset is a 32-bit integer.
    int Imm = (int)(MI.getOperand(FIOperandNum + 3).getImm());
    int Offset = FIOffset + Imm;
    assert((!Is64Bit || isInt<32>((long long)FIOffset + Imm)) &&
           "Requesting 64-bit offset in 32-bit immediate!");
    if (Offset != 0 || !tryOptimizeLEAtoMOV(II))
      MI.getOperand(FIOperandNum + 3).ChangeToImmediate(Offset);
  } else {
    // Offset is symbolic. This is extremely rare.
    uint64_t Offset = FIOffset +
      (uint64_t)MI.getOperand(FIOperandNum+3).getOffset();
    MI.getOperand(FIOperandNum + 3).setOffset(Offset);
  }
}

unsigned X86RegisterInfo::findDeadCallerSavedReg(
    MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI) const {
  const MachineFunction *MF = MBB.getParent();
  if (MF->callsEHReturn())
    return 0;

  const TargetRegisterClass &AvailableRegs = *getGPRsForTailCall(*MF);

  if (MBBI == MBB.end())
    return 0;

  switch (MBBI->getOpcode()) {
  default:
    return 0;
  case TargetOpcode::PATCHABLE_RET:
  case X86::RET:
  case X86::RET32:
  case X86::RET64:
  case X86::RETI32:
  case X86::RETI64:
  case X86::TCRETURNdi:
  case X86::TCRETURNri:
  case X86::TCRETURNmi:
  case X86::TCRETURNdi64:
  case X86::TCRETURNri64:
  case X86::TCRETURNmi64:
  case X86::EH_RETURN:
  case X86::EH_RETURN64: {
    SmallSet<uint16_t, 8> Uses;
    for (unsigned I = 0, E = MBBI->getNumOperands(); I != E; ++I) {
      MachineOperand &MO = MBBI->getOperand(I);
      if (!MO.isReg() || MO.isDef())
        continue;
      Register Reg = MO.getReg();
      if (!Reg)
        continue;
      for (MCRegAliasIterator AI(Reg, this, true); AI.isValid(); ++AI)
        Uses.insert(*AI);
    }

    for (auto CS : AvailableRegs)
      if (!Uses.count(CS) && CS != X86::RIP && CS != X86::RSP && CS != X86::ESP)
        return CS;
  }
  }

  return 0;
}

Register X86RegisterInfo::getFrameRegister(const MachineFunction &MF) const {
  const X86FrameLowering *TFI = getFrameLowering(MF);
  return TFI->hasFP(MF) ? FramePtr : StackPtr;
}

unsigned
X86RegisterInfo::getPtrSizedFrameRegister(const MachineFunction &MF) const {
  const X86Subtarget &Subtarget = MF.getSubtarget<X86Subtarget>();
  Register FrameReg = getFrameRegister(MF);
  if (Subtarget.isTarget64BitILP32())
    FrameReg = getX86SubSuperRegister(FrameReg, 32);
  return FrameReg;
}

unsigned
X86RegisterInfo::getPtrSizedStackRegister(const MachineFunction &MF) const {
  const X86Subtarget &Subtarget = MF.getSubtarget<X86Subtarget>();
  Register StackReg = getStackRegister();
  if (Subtarget.isTarget64BitILP32())
    StackReg = getX86SubSuperRegister(StackReg, 32);
  return StackReg;
}

static ShapeT getTileShape(Register VirtReg, VirtRegMap *VRM,
                           const MachineRegisterInfo *MRI) {
  if (VRM->hasShape(VirtReg))
    return VRM->getShape(VirtReg);

  const MachineOperand &Def = *MRI->def_begin(VirtReg);
  MachineInstr *MI = const_cast<MachineInstr *>(Def.getParent());
  unsigned OpCode = MI->getOpcode();
  switch (OpCode) {
  default:
    llvm_unreachable("Unexpected machine instruction on tile register!");
    break;
  case X86::COPY: {
    Register SrcReg = MI->getOperand(1).getReg();
    ShapeT Shape = getTileShape(SrcReg, VRM, MRI);
    VRM->assignVirt2Shape(VirtReg, Shape);
    return Shape;
  }
  // We only collect the tile shape that is defined.
  case X86::PTILELOADDV:
  case X86::PTILELOADDT1V:
  case X86::PTDPBSSDV:
  case X86::PTDPBSUDV:
  case X86::PTDPBUSDV:
  case X86::PTDPBUUDV:
  case X86::PTILEZEROV:
  case X86::PTDPBF16PSV:
    MachineOperand &MO1 = MI->getOperand(1);
    MachineOperand &MO2 = MI->getOperand(2);
    ShapeT Shape(&MO1, &MO2, MRI);
    VRM->assignVirt2Shape(VirtReg, Shape);
    return Shape;
  }
}

bool X86RegisterInfo::getRegAllocationHints(Register VirtReg,
                                            ArrayRef<MCPhysReg> Order,
                                            SmallVectorImpl<MCPhysReg> &Hints,
                                            const MachineFunction &MF,
                                            const VirtRegMap *VRM,
                                            const LiveRegMatrix *Matrix) const {
  const MachineRegisterInfo *MRI = &MF.getRegInfo();
  const TargetRegisterClass &RC = *MRI->getRegClass(VirtReg);
  bool BaseImplRetVal = TargetRegisterInfo::getRegAllocationHints(
      VirtReg, Order, Hints, MF, VRM, Matrix);

  if (RC.getID() != X86::TILERegClassID)
    return BaseImplRetVal;

  ShapeT VirtShape = getTileShape(VirtReg, const_cast<VirtRegMap *>(VRM), MRI);
  auto AddHint = [&](MCPhysReg PhysReg) {
    Register VReg = Matrix->getOneVReg(PhysReg);
    if (VReg == MCRegister::NoRegister) { // Not allocated yet
      Hints.push_back(PhysReg);
      return;
    }
    ShapeT PhysShape = getTileShape(VReg, const_cast<VirtRegMap *>(VRM), MRI);
    if (PhysShape == VirtShape)
      Hints.push_back(PhysReg);
  };

  SmallSet<MCPhysReg, 4> CopyHints;
  CopyHints.insert(Hints.begin(), Hints.end());
  Hints.clear();
  for (auto Hint : CopyHints) {
    if (RC.contains(Hint) && !MRI->isReserved(Hint))
      AddHint(Hint);
  }
  for (MCPhysReg PhysReg : Order) {
    if (!CopyHints.count(PhysReg) && RC.contains(PhysReg) &&
        !MRI->isReserved(PhysReg))
      AddHint(PhysReg);
  }

#define DEBUG_TYPE "tile-hint"
  LLVM_DEBUG({
    dbgs() << "Hints for virtual register " << format_hex(VirtReg, 8) << "\n";
    for (auto Hint : Hints) {
      dbgs() << "tmm" << Hint << ",";
    }
    dbgs() << "\n";
  });
#undef DEBUG_TYPE

  return true;
}